results
This model is a fine-tuned version of distilbert/distilbert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4245
- Precision: 0.7113
- Recall: 0.6599
- Accuracy: 0.7894
- F1: 0.6761
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 300
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | Accuracy | F1 |
---|---|---|---|---|---|---|---|
0.5719 | 1.0 | 145 | 0.7377 | 0.6165 | 0.6565 | 0.5837 | 0.5668 |
0.3644 | 2.0 | 290 | 0.6263 | 0.6649 | 0.7083 | 0.7228 | 0.6720 |
0.2425 | 3.0 | 435 | 0.7232 | 0.7070 | 0.5880 | 0.7786 | 0.5955 |
0.1122 | 4.0 | 580 | 0.9561 | 0.6698 | 0.6591 | 0.7610 | 0.6638 |
0.033 | 5.0 | 725 | 1.1062 | 0.6971 | 0.6520 | 0.7816 | 0.6664 |
0.0216 | 6.0 | 870 | 1.1311 | 0.6919 | 0.6445 | 0.7786 | 0.6589 |
0.0357 | 7.0 | 1015 | 1.2109 | 0.7091 | 0.6896 | 0.7884 | 0.6979 |
0.0367 | 8.0 | 1160 | 1.4296 | 0.6776 | 0.6762 | 0.7640 | 0.6769 |
0.0057 | 9.0 | 1305 | 1.3775 | 0.7088 | 0.6489 | 0.7875 | 0.6658 |
0.0004 | 10.0 | 1450 | 1.4245 | 0.7113 | 0.6599 | 0.7894 | 0.6761 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.3.1
- Tokenizers 0.21.0
- Downloads last month
- 2
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
๐
Ask for provider support